Changeset 58040

Timestamp:

04/24/2024 07:43:02 AM (7 months ago)

Author:

dmsnell

Message:

HTML API: Fix detection of single-length funky comments.

Since [60428] the Tag Processor has been misidentifying single-character
funky comments. It has been asserting that the full token-length for a
funky comment must be at least three characters after the opening (e.g.
</1>), but it has been starting to look for the closing > after
those same three characters. This means that it has been skipping the
actual close of these funky comments and swallowing up the next syntax
until it finds a >, often consuming the next tag in the process.

This patch fixes the detector and restores finding the following token.

Developed in ​https://github.com/WordPress/wordpress-develop/pull/6412
Discussed in https://core.trac.wordpress.org/ticket/60170

Follow-up to [60428].
Fixes #60170.
Props dmsnell, gziolo, jonsurrell.

Location:

trunk

Files:

• src/wp-includes/html-api/class-wp-html-tag-processor.php (modified) (4 diffs)
• tests/phpunit/tests/html-api/wpHtmlTagProcessor-token-scanning.php (modified) (1 diff)
• tests/phpunit/tests/interactivity-api/wpInteractivityAPI.php (modified) (1 diff)

trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php

@@ -1630 +1630 @@
              * https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
              */
-            if ( '!' === $html[ $at + 1 ] ) {
+            if ( ! $this->is_closing_tag && '!' === $html[ $at + 1 ] ) {
                 /*
                  * `<!--` transitions to a comment state – apply further comment rules.
@@ -1810 +1810 @@
              */
             if ( '>' === $html[ $at + 1 ] ) {
+                // `<>` is interpreted as plaintext.
+                if ( ! $this->is_closing_tag ) {
+                    ++$at;
+                    continue;
+                }
+
                 $this->parser_state         = self::STATE_PRESUMPTUOUS_TAG;
                 $this->token_length         = $at + 2 - $this->token_starts_at;
@@ -1820 +1826 @@
              * See https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
              */
-            if ( '?' === $html[ $at + 1 ] ) {
+            if ( ! $this->is_closing_tag && '?' === $html[ $at + 1 ] ) {
                 $closer_at = strpos( $html, '>', $at + 2 );
                 if ( false === $closer_at ) {
@@ -1892 +1898 @@
                 }
 
-                $closer_at = strpos( $html, '>', $at + 3 );
+                $closer_at = strpos( $html, '>', $at + 2 );
                 if ( false === $closer_at ) {
                     $this->parser_state = self::STATE_INCOMPLETE_INPUT;

trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor-token-scanning.php

@@ -762 +762 @@
 
     /**
+     * Ensures that various funky comments are properly parsed.
+     *
+     * @ticket 60170
+     *
+     * @since 6.6.0
+     *
+     * @covers WP_HTML_Tag_Processor::next_token
+     *
+     * @dataProvider data_various_funky_comments
+     *
+     * @param string $funky_comment_html HTML containing a funky comment.
+     * @param string $modifiable_text    Expected modifiable text of first funky comment in HTML.
+     */
+    public function test_various_funky_comments( $funky_comment_html, $modifiable_text ) {
+        $processor = new WP_HTML_Tag_Processor( $funky_comment_html );
+        while ( '#funky-comment' !== $processor->get_token_type() && $processor->next_token() ) {
+            continue;
+        }
+
+        $this->assertSame(
+            '#funky-comment',
+            $processor->get_token_type(),
+            'Failed to find the expected funky comment.'
+        );
+
+        $this->assertSame(
+            $modifiable_text,
+            $processor->get_modifiable_text(),
+            'Found the wrong modifiable text span inside a funky comment.'
+        );
+    }
+
+    /**
+     * Data provider.
+     *
+     * @return array[].
+     */
+    public static function data_various_funky_comments() {
+        return array(
+            'Space'          => array( '</ >', ' ' ),
+            'Short-bang'     => array( '</!>', '!' ),
+            'Question mark'  => array( '</?>', '?' ),
+            'Short-slash'    => array( '<//>', '/' ),
+            'Bit (no attrs)' => array( '<//wp:post-meta>', '/wp:post-meta' ),
+            'Bit (attrs)'    => array( '<//wp:post-meta key=isbn>', '/wp:post-meta key=isbn' ),
+            'Curly-wrapped'  => array( '</{json}>', '{json}' ),
+            'Before P'       => array( '</1><p>', '1' ),
+            'After P'        => array( '<p></__("Read more")></p>', '__("Read more")' ),
+            'Reference'      => array( '</&gt;>', '&gt;' ),
+        );
+    }
+
+    /**
      * Test helper that wraps a string in double quotes.
      *

trunk/tests/phpunit/tests/interactivity-api/wpInteractivityAPI.php

@@ -589 +589 @@
      *
      * @covers ::process_directives
-     */
-    public function test_process_directives_doesnt_change_html_if_contains_unbalanced_tags() {
+     *
+     * @dataProvider data_html_with_unbalanced_tags
+     *
+     * @param string $html HTML containing unbalanced tags and also a directive.
+     */
+    public function test_process_directives_doesnt_change_html_if_contains_unbalanced_tags( $html ) {
         $this->interactivity->state( 'myPlugin', array( 'id' => 'some-id' ) );
 
-        $html_samples = array(
-            '<div data-wp-bind--id="myPlugin::state.id">Inner content</div></div>',
-            '<div data-wp-bind--id="myPlugin::state.id">Inner content</div><div>',
-            '<div><div data-wp-bind--id="myPlugin::state.id">Inner content</div>',
-            '</div><div data-wp-bind--id="myPlugin::state.id">Inner content</div>',
-            '<div data-wp-bind--id="myPlugin::state.id">Inner<div>content</div>',
-            '<div data-wp-bind--id="myPlugin::state.id">Inner</div>content</div>',
-            '<div data-wp-bind--id="myPlugin::state.id"><span>Inner content</div>',
-            '<div data-wp-bind--id="myPlugin::state.id">Inner content</div></span>',
-            '<div data-wp-bind--id="myPlugin::state.id"><span>Inner content</div></span>',
-            '<div data-wp-bind--id="myPlugin::state.id">Inner conntent</ ></div>',
-        );
-
-        foreach ( $html_samples as $html ) {
-            $processed_html = $this->interactivity->process_directives( $html );
-            $p              = new WP_HTML_Tag_Processor( $processed_html );
-            $p->next_tag();
-            $this->assertNull( $p->get_attribute( 'id' ) );
-        }
+        $processed_html = $this->interactivity->process_directives( $html );
+        $p              = new WP_HTML_Tag_Processor( $processed_html );
+        $p->next_tag();
+        $this->assertNull( $p->get_attribute( 'id' ) );
+    }
+
+    /**
+     * Data provider.
+     *
+     * @return array[].
+     */
+    public static function data_html_with_unbalanced_tags() {
+        return array(
+            'DIV closer after'   => array( '<div data-wp-bind--id="myPlugin::state.id">Inner content</div></div>' ),
+            'DIV opener after'   => array( '<div data-wp-bind--id="myPlugin::state.id">Inner content</div><div>' ),
+            'DIV opener before'  => array( '<div><div data-wp-bind--id="myPlugin::state.id">Inner content</div>' ),
+            'DIV closer before'  => array( '</div><div data-wp-bind--id="myPlugin::state.id">Inner content</div>' ),
+            'DIV opener inside'  => array( '<div data-wp-bind--id="myPlugin::state.id">Inner<div>content</div>' ),
+            'DIV closer inside'  => array( '<div data-wp-bind--id="myPlugin::state.id">Inner</div>content</div>' ),
+            'SPAN opener inside' => array( '<div data-wp-bind--id="myPlugin::state.id"><span>Inner content</div>' ),
+            'SPAN closer after'  => array( '<div data-wp-bind--id="myPlugin::state.id">Inner content</div></span>' ),
+            'SPAN overlapping'   => array( '<div data-wp-bind--id="myPlugin::state.id"><span>Inner content</div></span>' ),
+        );
     }